# Creative Text Generation

Eurydice-24b v3 is a multi-character dialogue companion model built on Mistral 3.1, excelling in creative expression, natural conversation, and storytelling.

A powerful Titan-level model fusion, specifically designed to enhance role-playing, creativity, and intelligence.

A merged model based on Nitral-AI and LatitudeGames' two 12B parameter models, using the slerp fusion method, with powerful text generation capabilities

This is the result of task arithmetic fusion between Darkest-muse-v1 and gemma-2-9b-it-abliterated-LoRA-untied models using the mergekit tool

A large language model fine-tuned based on Llama-3-70B-Instruct, specializing in creative text generation and multi-task processing

SmolLM2-Prompt-Enhance is a text generation model fine-tuned based on SmolLM2-135M-Instruct, focusing on prompt enhancement tasks.

Violet_Twilight-v0.2 is a SLERP-merged model of Azure_Dusk-v0.2 and Crimson_Dawn-v0.2, supporting multilingual text generation tasks.

Violet_Twilight-v0.2 is a SLERP merged model of Azure_Dusk-v0.2 and Crimson_Dawn-v0.2, supporting multilingual text generation tasks.

KafkaLM 8b is a German large language model fine-tuned from Llama3 8b, specializing in German business scenarios

A 7B-parameter language model merged from Mistral 7B v0.1, combining multiple fine-tuned models via task arithmetic, supporting 32K context length, balancing creativity and reasoning

Jamba-Hercules is a fine-tuned large language model based on ai21labs/Jamba-v0.1, trained using the Locutusque/hercules-v4.0 dataset, focusing on text generation tasks.

A 7B parameter model focused on roleplay, with this merged version emphasizing enhanced creativity and reduced clichés.

A 7B-parameter large language model focused on role-playing, featuring 8192 context length with emphasis on creativity and reduced clichés

7-billion-parameter role-playing specialized model, incorporating features from high-quality models like Starling-LM, excels in vivid role-playing and precise instruction following

WestLake-7B-v2 is a 7-billion-parameter large language model specializing in role-playing and text generation, achieving an average score of 74.68 on the Open LLM Leaderboard.